DRAFT: fixes all read of the same data by having single reader broadcast

[bensonr]

Changes behavior of reads for data that is not domain specific. The approach is now to have a single MPI-rank read any data and broadcast it to the other members of a specified pelist. This is to help reduce impacts on a distributed filesystem for large core counts and small IOs.

Fixes # (will be added after testing)

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Please also note
any relevant details for your test configuration (e.g. compiler, OS). Include
enough information so someone can reproduce your tests.

Checklist:

Please check all whether they apply or not

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published in downstream modules

[laurenchilutti]

@bensonr do we still need to keep this PR open, or can we close?

[bensonr]

It is something we could still use, but I'll defer to the FV3 team as to whether they want this update.

[lharris4]

I am interested in anything that might improve initialization time for our increasingly high-resolution runs. Currently it takes about 10--15 minutes to initialize X-SHiELD (27.6K cores, io_layout=4,4) when reading the native-grid prescribed aerosol files.

Do we have any testing results that this change should indeed make reads for large core counts more efficient?